深度学习入门开源书，基于TensorFlow 2.0案例实战。Open source Deep Learning book, based on TensorFlow 2.0 framework.

This repository contains implementations and illustrative code to accompany DeepMind publications

Keras documentation, hosted live at keras.io

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019)

neural networks to learn Koopman eigenfunctions

This repository contains a number of Jupyter Notebooks illustrating different approaches to solve partial differential equations by means of neural networks using TensorFlow.

Linear and non-linear spectral forecasting algorithms

A brief tutorial on the Wasserstein auto-encoder

Deep Learning for Reduced Order Modelling

PyTorch Implementations of a VAE and a beta-VAE.

A library for dimensionality reduction on spatial-temporal PDE

Public tutorials of using Flow Forecast for forecasting and classifying time series data

A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks. arXiv:1804.09269

Enhancing Dynamic Mode Decomposition using Autoencoder Networks.

GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.

Update PDEKoopman code to Tensorflow 2

a multiresolution convolutional autoencoder architecture

Supporting code for "Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders"

Companion code for Data-Driven Resolvent Analysis

Attempt to speed Randomized SVD(Singular Value Decomposition) Using pytorch and it's gnu capabilities.

The unsupervised learning problem trains a diffeomorphic spatio-temporal grid, that registers the output sequence of the PDEs onto a non-uniform parameter/time-varying grid, such that the Kolmogoro…

Multi-fidelity reduced-order surrogate modeling

Time-series learning of latent-space dynamics for reduced-order model closure

Notebooks for UChicago Data Science Summer School lecture

ROM for convective-dominated models with applications to space weather.

Experiments with Hinton's recirculation algorithm for training autoencoders